{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IL4VJUBLA2I2GSEE2CACES5BWD","short_pith_number":"pith:IL4VJUBL","schema_version":"1.0","canonical_sha256":"42f954d02b0691a34884d080224ba1b0dc68ff85cbd74132331f3895a81b91eb","source":{"kind":"arxiv","id":"1805.07737","version":1},"attestation_state":"computed","paper":{"title":"Exp-Concavity of Proper Composite Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Parameswaran Kamalaruban, Robert C. Williamson, Xinhua Zhang","submitted_at":"2018-05-20T08:53:48Z","abstract_excerpt":"The goal of online prediction with expert advice is to find a decision strategy which will perform almost as well as the best expert in a given pool of experts, on any sequence of outcomes. This problem has been widely studied and $O(\\sqrt{T})$ and $O(\\log{T})$ regret bounds can be achieved for convex losses (\\cite{zinkevich2003online}) and strictly convex losses with bounded first and second derivatives (\\cite{hazan2007logarithmic}) respectively. In special cases like the Aggregating Algorithm (\\cite{vovk1995game}) with mixable losses and the Weighted Average Algorithm (\\cite{kivinen1999avera"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1805.07737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-20T08:53:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cacb480a030335e1361e3c778bc01a744bd385800f61d164d8be02c360cab0b4","abstract_canon_sha256":"b502e4318ec5d32d53a7adc8ba5b203ed9fb26f255e4e87b24c0363e32f057a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:32.680104Z","signature_b64":"RpznJGjHc1PxyV+YNY8FjvDXhMJ2pBrAMYh666FYcqgLz6wM8rBnYeRUg+MfV2WdN8VOXQbj3Z8VTKl1SV9CDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42f954d02b0691a34884d080224ba1b0dc68ff85cbd74132331f3895a81b91eb","last_reissued_at":"2026-05-18T00:15:32.679372Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:32.679372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exp-Concavity of Proper Composite Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Parameswaran Kamalaruban, Robert C. Williamson, Xinhua Zhang","submitted_at":"2018-05-20T08:53:48Z","abstract_excerpt":"The goal of online prediction with expert advice is to find a decision strategy which will perform almost as well as the best expert in a given pool of experts, on any sequence of outcomes. This problem has been widely studied and $O(\\sqrt{T})$ and $O(\\log{T})$ regret bounds can be achieved for convex losses (\\cite{zinkevich2003online}) and strictly convex losses with bounded first and second derivatives (\\cite{hazan2007logarithmic}) respectively. In special cases like the Aggregating Algorithm (\\cite{vovk1995game}) with mixable losses and the Weighted Average Algorithm (\\cite{kivinen1999avera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07737","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1805.07737","created_at":"2026-05-18T00:15:32.679493+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.07737v1","created_at":"2026-05-18T00:15:32.679493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07737","created_at":"2026-05-18T00:15:32.679493+00:00"},{"alias_kind":"pith_short_12","alias_value":"IL4VJUBLA2I2","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IL4VJUBLA2I2GSEE","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IL4VJUBL","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IL4VJUBLA2I2GSEE2CACES5BWD","json":"https://pith.science/pith/IL4VJUBLA2I2GSEE2CACES5BWD.json","graph_json":"https://pith.science/api/pith-number/IL4VJUBLA2I2GSEE2CACES5BWD/graph.json","events_json":"https://pith.science/api/pith-number/IL4VJUBLA2I2GSEE2CACES5BWD/events.json","paper":"https://pith.science/paper/IL4VJUBL"},"agent_actions":{"view_html":"https://pith.science/pith/IL4VJUBLA2I2GSEE2CACES5BWD","download_json":"https://pith.science/pith/IL4VJUBLA2I2GSEE2CACES5BWD.json","view_paper":"https://pith.science/paper/IL4VJUBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.07737&json=true","fetch_graph":"https://pith.science/api/pith-number/IL4VJUBLA2I2GSEE2CACES5BWD/graph.json","fetch_events":"https://pith.science/api/pith-number/IL4VJUBLA2I2GSEE2CACES5BWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IL4VJUBLA2I2GSEE2CACES5BWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IL4VJUBLA2I2GSEE2CACES5BWD/action/storage_attestation","attest_author":"https://pith.science/pith/IL4VJUBLA2I2GSEE2CACES5BWD/action/author_attestation","sign_citation":"https://pith.science/pith/IL4VJUBLA2I2GSEE2CACES5BWD/action/citation_signature","submit_replication":"https://pith.science/pith/IL4VJUBLA2I2GSEE2CACES5BWD/action/replication_record"}},"created_at":"2026-05-18T00:15:32.679493+00:00","updated_at":"2026-05-18T00:15:32.679493+00:00"}